CN112667760B - User travel activity track coding method - Google Patents
User travel activity track coding method Download PDFInfo
- Publication number
- CN112667760B CN112667760B CN202011551902.6A CN202011551902A CN112667760B CN 112667760 B CN112667760 B CN 112667760B CN 202011551902 A CN202011551902 A CN 202011551902A CN 112667760 B CN112667760 B CN 112667760B
- Authority
- CN
- China
- Prior art keywords
- functional
- area
- grid
- travel
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Navigation (AREA)
Abstract
The invention provides a user travel activity track coding method, which clusters position data of a user every day according to a space-time clustering method to obtain information of a plurality of stay points of the user every day; respectively carrying out first coding on the information of the plurality of stop points to obtain stop point coding information corresponding to the information of each stop point; screening long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out secondary coding on the long-term stay points to obtain user trip characteristic codes; performing function division on the trip area corresponding to the position data to obtain a function area division result; and carrying out third encoding on the trip characteristic codes of the users according to the functional area division result to obtain the final trip track information codes of the users. According to the method, the divided functional area characteristics and the user travel characteristic codes are combined through multiple coding, the travel track information codes of the users are finally obtained, and the multi-metadata can be effectively fused.
Description
Technical Field
The invention mainly relates to the technical field of track coding, in particular to a track coding method for travel activities of a user.
Background
With the continuous acceleration of the urbanization process, the number of infrastructure construction is greatly increased, the scale and the form of the city are continuously enlarged, a large number of mobile population is poured into the city, and the travel analysis requirements of different populations in the city become prominent.
Through collecting crowd's trip data, draw the trip chain of personnel in the region from crowd's trip data, further analyze different personnel's trip semanteme and find out the target crowd who has same kind of trip characteristic to know target crowd's distribution and have very high practical value to city planning, traffic management, safety precaution.
The conventional method for collecting the people's travel data (for example, common resident travel survey) has various survey data types, and besides travel-related data, the survey data also comprises resident individual data such as the place of household registration, sex, age, occupation, workplace and the like. Under the conditions that the original city is small in scale and the number of floating population is not large, the survey data can probably obtain good effect. However, with the continuous development of cities, the floating population is continuously poured in, the types of people with different functions in the cities become very complicated, and the work of counting the travel activity tracks of users is highly dependent on manpower. Data acquired by adopting a big data technology is relatively redundant, and the multi-element data cannot be effectively fused.
Disclosure of Invention
The invention aims to solve the technical problem of providing a user travel activity track coding method aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows: a method for encoding travel activity tracks of a user comprises the following steps:
clustering the position data of the user every day according to a space-time clustering method to obtain a plurality of stop point information of the user every day;
respectively carrying out first coding on the plurality of stop point information to obtain stop point coding information corresponding to each stop point information;
screening long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out secondary coding on the long-term stay points to obtain user travel characteristic codes;
performing function division on the trip area corresponding to the position data based on preset POI area interest data to obtain a function area division result corresponding to the trip area;
and carrying out third encoding on each user travel characteristic code according to the functional area division result to obtain a final travel track information code of the user.
Another technical solution of the present invention for solving the above technical problems is as follows: a user travel activity trajectory encoding device, comprising:
the clustering module is used for clustering the position data of the user every day according to a space-time clustering method to obtain the information of a plurality of stay points of the user every day;
the coding module is used for respectively carrying out first coding on the plurality of stay point information to obtain stay point coding information corresponding to each stay point information, screening out long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out second coding on the long-term stay points to obtain user trip characteristic codes;
the area dividing module is used for carrying out function division on the trip area corresponding to the position data based on preset POI area interest data to obtain a function area dividing result corresponding to the trip area;
and the coding module is further used for carrying out third coding on each user travel characteristic code according to the functional region division result to obtain a final travel track information code of the user.
Another technical solution of the present invention for solving the above technical problems is as follows: a user travel activity trajectory encoding device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, implementing the user travel activity trajectory encoding method as described above when the computer program is executed by the processor.
Another technical solution of the present invention for solving the above technical problems is as follows: a computer readable storage medium storing a computer program which, when executed by a processor, implements a user travel activity trajectory encoding method as described above.
The invention has the beneficial effects that: the method comprises the steps of obtaining daily stay point information of a user based on a space-time clustering method, automatically carrying out first coding and second coding on the stay point information to obtain a user travel characteristic code, carrying out function division on a region based on preset POI region interest data, carrying out third coding on the divided function region characteristic in combination with the user travel characteristic code to finally obtain a travel track information code of the user, and being capable of effectively fusing multi-element data to obtain a relatively accurate travel activity track code of the user, so that the method is convenient to be better applied to crowd travel track classification.
Drawings
Fig. 1 is a schematic flow chart of a user travel activity track encoding method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of the ratio entropy decision function region and the mixing region provided in the embodiment of the present invention;
fig. 3 is an overall data flow diagram of a user travel activity track encoding method according to an embodiment of the present invention;
fig. 4 is a functional module schematic diagram of a user travel activity track encoding method according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a method for encoding a user travel activity track includes the following steps:
s101: clustering the position data of the user every day according to a space-time clustering method to obtain a plurality of stop point information of the user every day;
s102: respectively carrying out first coding on the plurality of stop point information to obtain stop point coding information corresponding to each stop point information;
s103: screening long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out secondary coding on the long-term stay points to obtain user travel characteristic codes;
s104: performing function division on the trip area corresponding to the position data based on preset POI area interest data to obtain a function area division result corresponding to the trip area;
s105: and carrying out third encoding on each user travel characteristic code according to the functional area division result to obtain a final travel track information code of the user.
The parameters of the space-time clustering method are set as that the time threshold is 30 minutes (0.5h), and the space threshold is as follows: 600 m. And obtaining a plurality of daily stop point information of the user according to the existing space-time clustering method.
In the above embodiment, the daily stay point information of the user is obtained based on a space-time clustering method, the stay point information is automatically subjected to first coding and second coding to obtain the trip characteristic code of the user, the region is functionally divided based on preset POI region interest data, the divided functional region characteristics are combined with the trip characteristic code of the user to perform third coding, finally, the trip track information code of the user is obtained, the multi-element data can be effectively fused, more accurate trip activity track codes of the user are obtained, and the method is convenient to be better applied to crowd trip track classification.
Optionally, as an embodiment of the present invention, the process of respectively performing first encoding on the plurality of stop point information to obtain stop point encoding information corresponding to each stop point information includes:
recording the ith stop point informationIs slotiI takes the values of 1, 2 and 3 … … 48; and according to the preset coding frequency and the coding rule of DN 48bit, the slot of each day is codediPerforming first coding to obtain the stop point coding information corresponding to each stop point information, wherein DN represents slot of each dayiNumber, the 48bit is slotiThe length of the byte of the corresponding stop point coding information is as follows, the stop point coding information comprises 24-bit travel track codes and 24-bit area feature codes, wherein the travel track codes comprise 15-bit area grid number, 1-bit long-term stop point identification and 8-bit stop point and user travel initial point Home distance values, and the area feature codes comprise 1-bit function area identification, 3-bit function area judgment results and 20-bit user number in a travel area.
Specifically, the preset encoding frequency is once every half hour, i.e., once every 0.5 h.
In the above embodiment, each stop point information of the current day is first encoded according to the preset encoding frequency and the encoding rule of DN × 48bit to obtain the stop point encoded information, which is convenient for better processing the stop point encoded information in the later period.
Optionally, as an embodiment of the present invention, the process of screening long-term staying points from the staying points corresponding to the multiple staying point information according to the staying point coding information, and performing second coding on the long-term staying points to obtain the user travel feature code includes:
according to preset distance unit DisAScreening out the long-term stay point IsLSP according to the distance value between the stay point corresponding to the stay point coding information and the user trip starting point HomeA；
According to the longitude and latitude information (lng) of the stop pointA，latA) Establishing a mapping relation with the area grid, wherein the mapping relation is as follows:
wherein A is a dwell point, lngminAnd latminTo correct the parameters;
according to the preset distance unit DisAAnd the mapping relation is used for the long-term stopping point IsLSPAAnd carrying out second-time encoding, wherein the encoding formula is as follows:
Travel(sloti)＝{GridA,DisA,IsLSPA},
wherein, Travel (slot)i) And (4) encoding the trip characteristics of the user, wherein { } is a symbol for concatenating all information.
In the above embodiment, the longitude and latitude information of the dwell point is obtained from the grid number of the area where the dwell point is located in the dwell point coding information to judge the long-term dwell point, so that the user travel characteristic code containing the long-term dwell point information is obtained, and the long-term dwell point coding information can be conveniently fused with the area characteristics in the later period.
Optionally, as an embodiment of the present invention, the step of performing functional division on the travel area corresponding to the location data based on preset POI area interest data to obtain a functional area division result corresponding to the travel area includes:
carrying out grid division on the trip area according to a preset grid division value to obtain a plurality of grids;
performing functional division on the multiple grids based on preset POI region interest data to obtain multiple functional grids;
calculating a proportion value P (x) of the number N (x) of POIs in each functional grid to the total number of POIs in the total functional grid;
calculating a proportion value P '(x) of the number N' (x) of POIs in a functional grid of a nearby area of the travel area to the total number of POIs in a total functional grid, wherein the functional grid of the nearby area is a grid within a preset range value from the travel area;
calculating the probability ratio of the current functional grid in the outgoing area to all the functional grids in the nearby area, and carrying out normalization processing on the probability ratio to obtain a normalized value;
calculating an entropy value of the normalization value, and determining functional area judgment information of the current functional grid in the row area according to the entropy value;
and scoring the functional area judgment information corresponding to all the functional grids, and taking the functional area judgment information corresponding to the functional grid with the highest score as the functional area judgment result of the trip area.
In the above embodiment, the functional mesh is divided into regions in the form of a mesh, the functional mesh is scored, and the highest score is used as the result of determining the functional region of the region, so that the functional property of the region can be determined.
Optionally, as an embodiment of the present invention, the process of calculating a ratio p (x) of the number n (x) of POIs in each functional grid to the total number of POIs in the overall functional grid includes:
calculating a proportion value P (x) of the number N (x) of POIs in each functional grid to the total number of POIs in the total functional grid according to a first proportion formula, wherein the first proportion formula is as follows:
wherein, XiIs a functional grid, S is a set of functional grid types,
the total number of POIs is the total function grid.
Specifically, S ═ is a set of individual functional mesh types { Residential Area (RA), casual sports area (LA), Scenic Area (SA),...., Teaching Area (TA) }.
Specifically, before the functional region is encoded, the POI type is mapped to the functional region type: based on certain map POI category (type) data, obtaining a custom POI function category (feature) mapping rule f according to the custom mapping rule f, wherein the definition of the custom POI function category (feature) mapping rule f is as follows:
f：type→feature。
one mapping representation is shown in table one:
optionally, as an embodiment of the present invention, the calculating a ratio P '(x) of the number N' (x) of POIs in the functional mesh of the vicinity of the travel area to the total number of POIs in the overall functional mesh includes:
calculating a proportion value P '(x) of the number N' (x) of POIs in the functional grid of the nearby area of the area to the total number of POIs in the overall functional grid according to a second proportion formula, wherein the second proportion formula is as follows:
wherein, XiIs a functional grid, S is a set of functional grid types,
the total number of POIs is the total function grid.
Specifically, the area is mapped to the functional network (x, y), the functional zone type z, and N [ x ] [ y ] [ z ] is made 1. Let 1 Kilometer (KM) around be a nearby regional functional network.
In the above embodiment, the functional grids are divided into the types, and the types of the functional grids are integrated, so that it is convenient to determine what type of area the user travels for a long time.
Optionally, as an embodiment of the present invention, the calculating a probability ratio of the current functional mesh in the outgoing area to all functional meshes in the neighboring area, and performing normalization processing on the probability ratio to obtain a normalized value includes:
calculating the ratio of the functional area probability of the current functional grid and the functional grid of the nearby area according to a ratio formula, wherein the ratio formula is as follows:
wherein E (x) is a ratio;
normalizing the ratio according to a normalization formula, wherein the normalization formula is as follows:
where t (x) is the normalized value and S is the set of functional mesh types.
Optionally, as an embodiment of the present invention, the calculating an entropy value of the normalization value, and the determining the functional area determination information of the current functional grid in the row area according to the entropy value includes:
calculating an entropy value of the normalization value according to an entropy value calculation formula, wherein the entropy value calculation formula is as follows:
wherein H (p) is an entropy value, and T (x) is a normalized value;
and (3) judging that the current functional grid is a mixed region or a functional region according to the following formula by setting the entropy value of the current functional grid as H (A) and the threshold as epsilon:
wherein R (A) is the functional area judgment information.
In the above embodiment, each functional region is classified by using a weighted passing score algorithm by using ratio entropy to distinguish the functional region from the mixed region based on POI data.
FIG. 3 is a schematic flow chart of a ratio entropy decision function and a mixing region provided in an embodiment of the present invention;
the process of determining the functional region and the blend region by ratio entropy will be described in detail with reference to fig. 3.
S301: starting;
s302: self-defining mapping f: mapping the POI data type into a function area type, initializing the POI number N (x) in a function grid, N _ ground of a nearby grid, the function area statistical frequency P, the current area ratio entropy H and function area classification Result;
s303: inputting POI data;
s304: mapping location to network (x, y), functional zone type z, and making N [ x ] [ y ] [ z ] ═ 1;
s305: initializing a variable i ═ 0 and a variable j ═ 0;
s306: counting the frequencies (N _ group of nearby grids) of various functional areas of 1 Kilometer (KM) around the grids (i, j);
s307: calculating the frequency N, P ═ N/N _ ground of each functional area in the grid (i, j), namely: calculating the proportion value of the number N (x) of POIs in each functional grid to the total number of POIs in the total functional grid according to a first proportion formula
And calculating the proportion value of the number N' (x) of POIs in the functional grid of the nearby area of the area to the total number of POIs in the total functional grid according to a second proportion formula
Calculating the ratio of the functional area probability of the current functional grid to the functional grid in the nearby area, and normalizing the ratio to obtain a normalized value
S308: calculating a ratio entropy H;
s309: judging whether the ratio entropy H is larger than a threshold value, if so, finding a Result [ i ] [ j ] (mixed area), and if not, obtaining a functional area r with the largest ratio according to P;
S310：Result[i][j]＝r；
s311: judging whether all the grid traversals are finished, if not, assigning the (i, j) to be the next network, and returning to the SS 6; if yes, outputting the functional partitions corresponding to all grids;
s312: and (6) ending.
In the above process, the functional area determination is performed on each network in the area to obtain the functional partition result corresponding to each mesh.
Optionally, as an embodiment of the present invention, the scoring the functional area determination information corresponding to all the functional grids, and taking the functional area determination information corresponding to the functional grid with the highest score as the functional area determination result of the travel area includes:
setting a trip area as A, and carrying out scoring calculation on the functional area judgment information corresponding to all the functional grids according to a scoring formula, wherein the scoring formula is as follows:
Fi(A)＝numi(A)*factori+aroundResulti(A)*aroundFactori，i∈S，
wherein, Fi(A) Sum of scores, num, of class i functional zones representing travel area Ai(A) Representing the number of POIs, factors, in the travel area A, containing the i-th type functional areaiA weight factor, aroundResult, representing the i-th class of functional zonesi(A) The sum of scores, arondfactor, of the ith functional mesh representing the vicinity of the travel area AiA transport impact factor representing a class i functional region;
calculating the score ratio SC of the functional area corresponding to each functional grid according to the score judgment formulai(A) The scoring judgment formula is as follows:
SC with highest scorei(A) As a result of the functional area determination of the travel area a.
In the above embodiment, the functional area determination result is determined according to the functional area score with the highest score, so that the accuracy of the result is improved.
Optionally, as an embodiment of the present invention, the third encoding of each user travel feature code according to the functional region division result to obtain a final travel trajectory information code of the user includes:
and carrying out third-time coding on each user trip characteristic code according to the functional area division result, wherein the coding formula is as follows:
Encode(sloti)＝{Travel(sloti)，Area(sloti)}
＝{GridA，DisA，IsLSPA，R(A)，RT(A)，RN(A)}，
wherein, Travel (slot)i) Coding the trip characteristics of the user, Area (slot)i) Area (slot) as a regional featurei) (r), (a), rt (a), rn (a), and r (a) are mixed region determination results, rt (a) is functional region determination results, rn (a) is the number of users staying in the row region, and {, } is a symbol for concatenating each piece of information;
collecting third-time codes obtained by the user travel characteristic codes, and using Encode (user) as a final travel track information code of the user, wherein the travel track information code is as follows: encode (user) { Encode (slot)i)}，slotiE S, wherein S is a set of functional grid types.
In the above embodiment, the travel characteristics and the regional characteristics are integrated, that is, the divided functional regional characteristics are combined with the travel characteristic codes of the user to perform third coding, and finally, the travel track information codes of the user are obtained, so that the multi-element data can be effectively fused.
It should be appreciated that the behavioral activity track encoding for a user for a number of consecutive days can be derived for all sampling encoding instants according to the above-described method.
Fig. 2 is an overall data flow diagram of a user travel activity track encoding method according to an embodiment of the present invention.
The whole track encoding process is specifically described below with reference to fig. 2:
s201: starting;
s202: inputting multi-source position data such as track data of a certain day of a user and preset POI region interest data;
s203: extracting and marking a long-term stop point set LSP of a user in the track data: clustering the daily trip area data of the user according to a space-time clustering method to obtain a plurality of daily stay point information of the user, respectively carrying out first coding on the plurality of stay point information according to a coding rule to obtain the stay point coding information corresponding to each stay point information, and respectively determining a long-term stay point according to each stay point coding information, wherein the parameters of the space-time clustering method are set as a time threshold value of 30 minutes (0.5h), and a space threshold value is: 600 meters;
s204: setting: initializing a variable i to 1; initializing all 0 of coding time [ i ]; initializing each code sampling time length to be 0.5 h;
s205: recording the ith stop point information as slotiCorresponding long term dwell point IsLSPAAnd corresponding area A, according to the long-term dwell point IsLSPAThe travel characteristics of the user are coded for the second time according to the preset coding frequency, namely each long-term dwell point IsLSPAEncoding the data once every 0.5 h;
s206: generating Travel characteristic Travel (slot)i)；
S207: calculating the ratio of the probability of the functional areas of the current functional grid and the functional grid in the nearby area in the area A, carrying out normalization processing on the ratio to obtain a normalization value, calculating an entropy value H of the normalization value, and determining the functional area judgment information of the current functional grid according to the entropy value;
s208: judging whether H is larger than a threshold value epsilon, if so, judging that H is a mixed area, and if not, judging that H is a final functional area;
s209: computing regional feature Area (slot)i)，Area(sloti)＝{R(A)，RT(A)，RN(A)}；
S210: thirdly encoding the trip characteristic code of the user according to the judgment result of the functional area to obtain the final trip track information code of the grid of the functional area;
s211: judging whether the variable i is smaller than 48, if so, returning the variable i +1 to S5 for the next encoding, and jumping out of the loop until the variable i is equal to 48;
s212: generating a travel track code of the user on the same day: collecting the third codes obtained by the user travel characteristic codes, using a set S as the final travel track information code of the functional area grid, and enabling the travel trackThe trace information is encoded as an Encode (user) ═ Encode (slot)i)}，sloti∈S；
S213: and (6) ending.
Alternatively, as another embodiment of the present invention, as shown in fig. 4, an apparatus for encoding a user travel activity track includes:
the clustering module is used for clustering the position data of the user every day according to a space-time clustering method to obtain the information of a plurality of stay points of the user every day;
the coding module is used for respectively carrying out first coding on the plurality of stay point information to obtain stay point coding information corresponding to each stay point information, screening out long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out second coding on the long-term stay points to obtain user trip characteristic codes;
the area dividing module is used for carrying out function division on the trip area corresponding to the position data based on preset POI area interest data to obtain a function area dividing result corresponding to the trip area;
and the coding module is further used for carrying out third coding on each user travel characteristic code according to the functional region division result to obtain a final travel track information code of the user.
Optionally, as another embodiment of the present invention, a user travel activity track coding apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the user travel activity track coding method as described above is implemented.
Alternatively, as another embodiment of the present invention, a computer-readable storage medium stores a computer program, which when executed by a processor, implements the user travel activity trajectory encoding method as described above.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A method for encoding travel activity tracks of a user is characterized by comprising the following steps:
clustering the position data of the user every day according to a space-time clustering method to obtain a plurality of stop point information of the user every day;
respectively carrying out first coding on the plurality of stop point information to obtain stop point coding information corresponding to each stop point information;
screening long-term stay points from the stay points corresponding to the plurality of stay point information according to the stay point coding information, and carrying out secondary coding on the long-term stay points to obtain user travel characteristic codes;
performing function division on the trip area corresponding to the position data based on preset POI area interest data to obtain a function area division result corresponding to the trip area; the method specifically comprises the following steps: carrying out grid division on the trip area according to a preset grid division value to obtain a plurality of grids;
performing functional division on the multiple grids based on preset POI region interest data to obtain multiple functional grids;
calculating a proportion value P (x) of the number N (x) of POIs in each functional grid to the total number of POIs in the total functional grid;
calculating a proportion value P '(x) of the number N' (x) of POIs in a functional grid of a nearby area of the travel area to the total number of POIs in a total functional grid, wherein the functional grid of the nearby area is a grid within a preset range value from the travel area;
calculating the probability ratio of the current functional grid in the outgoing area to all the functional grids in the nearby area, and carrying out normalization processing on the probability ratio to obtain a normalized value;
calculating an entropy value of the normalization value, and determining functional area judgment information of the current functional grid in the row area according to the entropy value;
scoring the functional area judgment information corresponding to all the functional grids, and taking the functional area judgment information corresponding to the functional grid with the highest score as the functional area judgment result of the trip area;
thirdly encoding each user travel characteristic code according to the functional area division result to obtain a final travel track information code of the user; the method specifically comprises the following steps:
and carrying out third-time coding on each user trip characteristic code according to the functional area division result, wherein the coding formula is as follows:
Encode(sloti)＝{Travel(sloti)，Area(sloti)}
＝{GridA，DisA，IsLSPA，R(A)，RT(A)，RN(A)}，
wherein, Travel (slot)i) Coding the trip characteristics of the user, Area (slot)i) Area (slot) as a regional featurei)＝{R(A)，RT(A)，RN(A)}，GridAFor the mapping relationship between the stopping point A and the grid of the region, DisAFor a predetermined distance unit, IsLSPAFor the long-term staying point, R (A) is the mixed region judgment result, RT (A) is the functional region judgment result, RN (A) is the number of users staying in the outgoing region {,the symbol is used for connecting all information in series;
collecting third-time codes obtained by the user travel characteristic codes, and using Encode (user) as a final travel track information code of the user, wherein the travel track information code is as follows:
Encode(user)＝{Encode(sloti)}，slotie S, where S is a set of functional grid types.
2. The method for encoding a user travel activity trajectory according to claim 1, wherein the step of encoding the plurality of stay point information for the first time to obtain the stay point encoded information corresponding to each stay point information comprises:
recording the ith stop point information as slotiI takes the values of 1, 2 and 3 … … 48; and according to the preset coding frequency and the coding rule of DN 48bit, the slot of each day is codediPerforming first coding to obtain the stop point coding information corresponding to each stop point information, wherein DN represents slot of each dayiNumber, the 48bit is slotiThe length of the byte of the corresponding stop point coding information is as follows, the stop point coding information comprises 24-bit travel track codes and 24-bit area feature codes, wherein the travel track codes comprise 15-bit area grid number, 1-bit long-term stop point identification and 8-bit stop point and user travel initial point Home distance values, and the area feature codes comprise 1-bit function area identification, 3-bit function area judgment results and 20-bit user number in a travel area.
3. The method for encoding user travel activity trajectories according to claim 2, wherein the step of screening long-term dwell points from the dwell points corresponding to the plurality of dwell point information according to dwell point encoding information, and performing second encoding on the long-term dwell points to obtain user travel feature codes comprises:
according to preset distance unit DisAScreening the distance value between the stay point corresponding to the stay point coding information and the user trip starting point HomeGo out long-term dwell point IsLSPA；
According to the longitude and latitude information (lng) of the stop pointA，latA) Establishing a mapping relation with the area grid, wherein the mapping relation is as follows:
wherein A is a dwell point, lngAFor longitude information of stop point A, latALng as latitude information of dwell point AminAnd latminTo correct the parameters;
according to the preset distance unit DisAAnd the mapping relation is used for the long-term stopping point IsLSPAAnd carrying out second-time encoding, wherein the encoding formula is as follows:
Travel(sloti)＝{GridA，DisA，IsLSPA}，
wherein, Travel (slot)i) Coding the trip characteristics of the user, wherein GridAFor the mapping relationship between the stopping point A and the grid of the region, DisAFor a predetermined distance unit, IsLSPAFor the long-term dwell point, {, } is the symbol that concatenates the individual messages.
4. A travel activity trajectory encoding method as claimed in claim 1, wherein said calculating a ratio p (x) of the number n (x) of POIs in each functional mesh to the total number p (x) of POIs in the overall functional mesh comprises:
calculating a proportion value P (x) of the number N (x) of POIs in each functional grid to the total number of POIs in the total functional grid according to a first proportion formula, wherein the first proportion formula is as follows:
wherein, XiIs a functional grid, S is a set of functional grid types,
the total number of POIs is the total function grid.
5. A travel activity trajectory encoding method as claimed in claim 4, wherein said calculating a ratio P '(x) of the number N' (x) of POIs in the functional mesh of the vicinity area of the travel area to the total number of POIs in the functional mesh of the general functional mesh comprises:
calculating a proportion value P '(x) of the number N' (x) of POIs in the functional grid of the nearby area of the area to the total number of POIs in the overall functional grid according to a second proportion formula, wherein the second proportion formula is as follows:
wherein, XiIs a functional grid, S is a set of functional grid types,
the total number of POIs is the total function grid.
6. A travel activity trajectory coding method according to claim 5, wherein the calculating of the probability ratio of the current functional mesh in the travel region to all functional meshes in the vicinity region and the normalizing of the probability ratio to obtain the normalized value includes:
calculating the ratio of the functional area probability of the current functional grid and the functional grid of the nearby area according to a ratio formula, wherein the ratio formula is as follows:
wherein E (x) is a ratio;
normalizing the ratio according to a normalization formula, wherein the normalization formula is as follows:
where t (x) is the normalized value and S is the set of functional mesh types.
7. The travel activity trajectory encoding method according to claim 6, wherein the calculating of the entropy of the normalization value and the determining of the functional area determination information of the current functional mesh in the travel area according to the entropy includes:
calculating an entropy value of the normalization value according to an entropy value calculation formula, wherein the entropy value calculation formula is as follows:
wherein H (p) is an entropy value, and T (x) is a normalized value;
and (3) judging that the current functional grid is a mixed region or a functional region according to the following formula by setting the entropy value of the current functional grid as H (A) and the threshold as epsilon:
wherein R (A) is the functional area judgment information.
8. A travel activity trajectory encoding method according to claim 7, wherein the step of scoring all the functional area determination information corresponding to the functional meshes and using the functional area determination information corresponding to the functional mesh with the highest score as the functional area determination result of the travel area comprises:
setting a trip area as A, and carrying out scoring calculation on the functional area judgment information corresponding to all the functional grids according to a scoring formula, wherein the scoring formula is as follows:
Fi(A)＝numi(A)*factori+aroundResulti(A)*aroundFactori，i∈S，
wherein, Fi(A) Sum of scores, num, of class i functional zones representing travel area Ai(A) Representing the number of POIs, factors, in the travel area A, containing the i-th type functional areaiA weight factor, aroundResult, representing the i-th class of functional zonesi(A) The sum of scores, arondfactor, of the ith functional mesh representing the vicinity of the travel area AiA transport impact factor representing a class i functional region;
calculating the score ratio SC of the functional area corresponding to each functional grid according to the score judgment formulai(A) The scoring judgment formula is as follows:
SC with highest scorei(A) As a result of the functional area determination of the travel area a.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011551902.6A CN112667760B (en) | 2020-12-24 | 2020-12-24 | User travel activity track coding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011551902.6A CN112667760B (en) | 2020-12-24 | 2020-12-24 | User travel activity track coding method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112667760A CN112667760A (en) | 2021-04-16 |
| CN112667760B true CN112667760B (en) | 2022-03-29 |
Family
ID=75408391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011551902.6A Active CN112667760B (en) | 2020-12-24 | 2020-12-24 | User travel activity track coding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112667760B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113556698A (en) * | 2021-07-21 | 2021-10-26 | 智慧足迹数据科技有限公司 | Information clustering method, device, equipment and medium based on mobile phone signaling |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709419A (en) * | 2016-11-18 | 2017-05-24 | 中山大学 | Video human behavior recognition method based on significant trajectory spatial information |
| CN107133269A (en) * | 2017-04-01 | 2017-09-05 | 中国人民解放军国防科学技术大学 | Frequent location track generation method and device based on mobile target |
| CN109005515A (en) * | 2018-09-05 | 2018-12-14 | 武汉大学 | A method of the user behavior pattern portrait based on motion track information |
| CN109523186A (en) * | 2018-11-28 | 2019-03-26 | 杭州中奥科技有限公司 | Urban area partitioning method and device |
| CN110516708A (en) * | 2019-07-23 | 2019-11-29 | 江苏大学 | A kind of path prediction technique based on track and road network |
| CN110956188A (en) * | 2018-09-26 | 2020-04-03 | 北京融信数联科技有限公司 | Population behavior track digital coding method based on mobile communication signaling data |
| CN111582948A (en) * | 2020-05-25 | 2020-08-25 | 北京航空航天大学 | Individual behavior analysis method based on mobile phone signaling data and POI (Point of interest) |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160116985A1 (en) * | 2014-09-30 | 2016-04-28 | Purdue Research Foundation | Universal translator for recognizing nonstandard gestures |
-
2020
- 2020-12-24 CN CN202011551902.6A patent/CN112667760B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709419A (en) * | 2016-11-18 | 2017-05-24 | 中山大学 | Video human behavior recognition method based on significant trajectory spatial information |
| CN107133269A (en) * | 2017-04-01 | 2017-09-05 | 中国人民解放军国防科学技术大学 | Frequent location track generation method and device based on mobile target |
| CN109005515A (en) * | 2018-09-05 | 2018-12-14 | 武汉大学 | A method of the user behavior pattern portrait based on motion track information |
| CN110956188A (en) * | 2018-09-26 | 2020-04-03 | 北京融信数联科技有限公司 | Population behavior track digital coding method based on mobile communication signaling data |
| CN109523186A (en) * | 2018-11-28 | 2019-03-26 | 杭州中奥科技有限公司 | Urban area partitioning method and device |
| CN110516708A (en) * | 2019-07-23 | 2019-11-29 | 江苏大学 | A kind of path prediction technique based on track and road network |
| CN111582948A (en) * | 2020-05-25 | 2020-08-25 | 北京航空航天大学 | Individual behavior analysis method based on mobile phone signaling data and POI (Point of interest) |
Non-Patent Citations (1)
| Title |
|---|
| "一种基于空间编码技术的轨迹特征提取方法";乔少杰 等;《中国科学：信息科学》;20171110;第47卷(第11期);第1524-2537页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112667760A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shashaani et al. | Multi-stage prediction for zero-inflated hurricane induced power outages | |
| Ranjan et al. | Performance evaluation of Indian states in tourism using an integrated PROMETHEE-GAIA approach | |
| Burdziej | Using hexagonal grids and network analysis for spatial accessibility assessment in urban environments–a case study of public amenities in Toruń | |
| CN112035584A (en) | Space planning scene simulation method and system | |
| AIlard et al. | Targeting crime prevention to reduce offending: Identifying communities that generate chronic and costly offenders | |
| CN116451931B (en) | Data processing method for public service facility site selection administrative management decision | |
| CN112667760B (en) | User travel activity track coding method | |
| CN112651546A (en) | Bus route optimization method and system | |
| Sun et al. | How the natural environment in downtown neighborhood affects physical activity and sentiment: Using social media data and machine learning | |
| Wang et al. | Influence of built environment on subway trip origin and destination: insights based on mobile positioning data | |
| CN112836890A (en) | Method, device, equipment and storage medium for predicting fire risk | |
| Zhou et al. | Big data for intrametropolitan human movement studies A case study of bus commuters based on smart card data | |
| CN116975463A (en) | Travel purpose prediction method, prediction model training method, equipment and storage medium | |
| Luo et al. | Modeling urban growth with geographically weighted multinomial logistic regression | |
| CN116244395A (en) | Regional type discriminating method, device and equipment based on urban road and POI data | |
| Gomes et al. | Measuring happyiness and wellbeing in smart cities | |
| Williams et al. | Wider Factors affecting the long-term growth in Rail Travel | |
| CN112668858A (en) | Method, device, equipment and storage medium for determining target station in area | |
| CN116756439B (en) | Address selection method, device, server and computer readable storage medium | |
| Harris | 10 Population mapping by geodemographics and digital imagery | |
| Gao et al. | Integrating multi-source geographic big data to delineate urban growth boundary: A case study of Changsha | |
| Stoica et al. | Perspectives for the Development of Sustainable Cultural Tourism. Sustainability 2022, 14, 5678 | |
| CN117493981B (en) | Tourist classification method and device and electronic equipment | |
| Choi et al. | Differential Dynamics of Transit Use Resilience During the COVID-19 Pandemic Using Multivariate Two-Dimensional Functional Data Analysis | |
| CN114386529B (en) | Community service analysis method and system based on big data and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 101101 building 4, courtyard 57, Yunhe East Street, Tongzhou District, Beijing Applicant after: Beijing Academy of emergency management science and technology Applicant after: Beihang University Address before: 101101 building 4, courtyard 57, Yunhe East Street, Tongzhou District, Beijing Applicant before: BEIJING ACADEMY OF SAFETY SCIENCE AND TECHNOLOGY Applicant before: Beihang University |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |